Background: When applying genomic medicine to a rare disease patient, the primary goal is to identify one or more genomic variants that may explain the patient's phenotypes. Typically, this is done through annotation, filtering, and then prioritization of variants for manual curation. However, prioritization of variants in rare disease patients remains a challenging task due to the high degree of variability in phenotype presentation and molecular source of disease. Thus, methods that can identify and/or prioritize variants to be clinically reported in the presence of such variability are of critical importance. Methods: We tested the application of classification algorithms that ingest variant annotations along with phenotype information for predicting whether a variant will ultimately be clinically reported and returned to a patient. To test the classifiers, we performed a retrospective study on variants that were clinically reported to 237 patients in the Undiagnosed Diseases Network. Results: We treated the classifiers as variant prioritization systems and compared them to four variant prioritization algorithms and two single-measure controls. We showed that the trained classifiers outperformed all other tested methods with the best classifiers ranking 72% of all reported variants and 94% of reported pathogenic variants in the top 20. Conclusions: We demonstrated how freely available binary classification algorithms can be used to prioritize variants even in the presence of real-world variability. Furthermore, these classifiers outperformed all other tested methods, suggesting that they may be well suited for working with real rare disease patient datasets.